# dair-ai/ML-Notebooks

:fire: Machine Learning Notebooks

Repository: https://github.com/dair-ai/ML-Notebooks
Canonical: https://ross.abutalabs.com/products/ml-notebooks
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: deep-learning, machine-learning, python, pytorch, ai
Last push: 2024-04-09T15:11:49+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1621, "days_push": 876, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3436, forks 538 (observed 2026-08-28T04:08:04.969164+00:00)

## What it is
A collection of minimal, reusable Jupyter notebooks covering machine learning and deep learning tasks, built primarily with PyTorch. It serves as an educational resource with runnable examples in Colab or GitHub Codespaces.

## Use cases
- learn pytorch with hands-on notebooks
- machine learning tutorials for beginners
- implement linear regression from scratch
- understand computational graphs
- learn explainable AI with counterfactual explanations
- find reusable ML notebook examples

## When to choose
- you want minimal, runnable PyTorch examples to learn from
- you prefer notebook-based, hands-on learning
- you need educational material for ML courses or self-study

## When to avoid
- you need production-ready ML code or pipelines
- you want a maintained library or framework with an API
- you need coverage of advanced or specialized ML topics

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, developer-tools
- domain: machine-learning, deep-learning, education, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, pytorch, educational, colab, hands-on-tutorials, web

## Member repositories
- dair-ai/ML-Notebooks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:04.969164+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:37:41.928508+00:00, confidence not recorded.
  - readme: https://github.com/dair-ai/ML-Notebooks (fetched 2026-08-28T04:08:04.969164+00:00, sha acbd40b68dce)
- Data as of 2026-08-30T08:39:29.467469+00:00.